This advances the validation cycle because, as vehicle platforms become increasingly software defined, engineering teams must manage large volumes of requirements, engineering data and system specifications while ensuring full consistency and traceability.
The STG Agent, developed with the AWS Generative AI Innovation Center using Amazon Nova foundation models, Amazon Bedrock Knowledge Bases, and the Strands Agents framework, helps Marelli to improve efficiency and boost consistency in how product features are validated against customer requirements.
The new tool aims to reduce validation time and to achieve stronger alignment between system requirements and validated product behaviors.
This may help vehicle makers to accelerate product development especially for software-defined vehicles and to deliver new functionalities with greater reliability.
The Agent is also designed for seamless integration with requirement management tools, supporting compatibility with existing automotive engineering workflows.
Within Marelli’s established development process, customer requirements are first translated by R&D engineers into system requirements — a human-driven step that defines what the product must do.
The STG Agent then comes into play: it analyzes and identifies the expected behaviours implied by each system requirement and automatically generates corresponding clear, structured, traceable system test cases that support Marelli engineers in validating that each feature behaves as intended.
See all our Test & Measurement content.
